pm-competitors-intel

Multi-host portability rules. When invoking AskUserQuestion:

1. The header field MUST be a short noun phrase (≤ 12 characters). Mistral Vibe rejects longer headers with string_too_long. Pick from: Start, Target, Scope, Audience, Methodology, Feature, Question.
2. The options list MUST have at least 2 items. Vibe rejects empty/single-option calls. For free-text input, always provide ≥ 2 framing options (e.g. Yes, here's the input / Skip) — never call ask_user_question with options: [].

Preamble (run first)

source ~/.nanopm/lib/nanopm.sh 2>/dev/null || \
  source .nanopm/lib/nanopm.sh 2>/dev/null || \
  { echo "ERROR: nanopm not installed. Run: curl -fsSL https://raw.githubusercontent.com/nmrtn/nanopm/main/setup | bash"; exit 1; }
nanopm_preamble
_INTEL_DIR=".nanopm/raw/competitors"
_SNAPSHOT_DIR=".nanopm/raw/competitors/snapshots"
_COMPETITORS_FILE=".nanopm/raw/competitors/competitors.json"
mkdir -p "$_INTEL_DIR" "$_SNAPSHOT_DIR"

# Mode routing. The default run is the cheap diff veille (one diff subagent).
# An "analyze" keyword in the skill arguments preselects the heavy analysis
# (SWOT + positioning matrix). Phase 1 also offers the same mode via menu, so
# both paths converge on _MODE=analyze. With no keyword and no menu choice,
# _MODE stays "diff" — behaviour is unchanged, no extra agents, no cost regression.
_MODE="diff"
case "$(echo "${ARGUMENTS:-}" | tr '[:upper:]' '[:lower:]')" in
  *analyze*|*analyse*|*deep*|*landscape*) _MODE="analyze" ;;
esac
echo "MODE: $_MODE"

Phase 0: Prior context

source ~/.nanopm/lib/nanopm.sh 2>/dev/null || source .nanopm/lib/nanopm.sh 2>/dev/null || true
nanopm_context_read pm-competitors-intel

If a prior entry exists, show: "Last intel run: {ts}. Checking for changes since then."

Pull the Define/Plan context through the query primitive so the report compares us-vs-them on real positioning instead of a guess — one read-side call that synthesizes the relevant wiki pages instead of bespoke per-doc reads (the recipe pattern: query → reasoning → ingest). The raw docs stay out of this run; you reason over the cited synthesis the query returns. Print the prompt and dispatch it with the Agent tool (one subagent); on a host with no Agent tool, follow its steps inline.